Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compress
    -0.07
    ück
    -0.07
     strikes
    -0.06
     lav
    -0.06
     додатков
    -0.06
     emailing
    -0.06
     Rand
    -0.06
     kuvvet
    -0.06
     Yak
    -0.06
     effectiveness
    -0.06
    POSITIVE LOGITS
     NOT
    0.09
    wpdb
    0.07
     stringByAppending
    0.07
    .firstChild
    0.06
    fonts
    0.06
     norms
    0.06
     Stef
    0.06
     ук
    0.06
    Tasks
    0.06
     nextState
    0.06
    Act Density 0.004%

    No Known Activations